-
公开(公告)号：US20210319256A1
公开(公告)日：2021-10-14
申请号：US17332773
申请日：2021-05-27
Applicant: Adobe Inc.
Inventor： Xin Sun , Sohrab Amirghodsi , Nathan Carr , Michal Lukac
Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating a modified digital image by identifying patch matches within a digital image utilizing a Gaussian mixture model. For example, the systems described herein can identify sample patches and corresponding matching portions within a digital image. The systems can also identify transformations between the sample patches and the corresponding matching portions. Based on the transformations, the systems can generate a Gaussian mixture model, and the systems can modify a digital image by replacing a target region with target matching portions identified in accordance with the Gaussian mixture model.
-
公开(公告)号：US20200342634A1
公开(公告)日：2020-10-29
申请号：US16392968
申请日：2019-04-24
Applicant: Adobe Inc.
Inventor： Connelly Barnes , Sohrab Amirghodsi , Michal Lukac , Elya Shechtman , Ning Yu
Abstract: Techniques are disclosed for neural network based interpolation of image textures. A methodology implementing the techniques according to an embodiment includes training a global encoder network to generate global latent vectors based on training texture images, and training a local encoder network to generate local latent tensors based on the training texture images. The method further includes interpolating between the global latent vectors associated with each set of training images, and interpolating between the local latent tensors associated with each set of training images. The method further includes training a decoder network to generate reconstructions of the training texture images and to generate an interpolated texture based on the interpolated global latent vectors and the interpolated local latent tensors. The training of the encoder and decoder networks is based on a minimization of a loss function of the reconstructions and a minimization of a loss function of the interpolated texture.
-
公开(公告)号：US10762680B1
公开(公告)日：2020-09-01
申请号：US16363839
申请日：2019-03-25
Applicant: Adobe Inc.
Inventor： Sohrab Amirghodsi , Connelly Barnes , Eric L. Palmer
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating deterministic enhanced digital images based on parallel determinations of pixel group offsets arranged in pixel waves. For example, the disclosed systems can utilize a parallel wave analysis to propagate through pixel groups in a pixel wave of a target region within a digital image to determine matching patch offsets for the pixel groups. The disclosed systems can further utilize the matching patch offsets to generate a deterministic enhanced digital image by filling or replacing pixels of the target region with matching pixels indicated by the matching patch offsets.
-
公开(公告)号：US10586311B2
公开(公告)日：2020-03-10
申请号：US15921457
申请日：2018-03-14
Applicant: ADOBE INC.
Inventor： Sohrab Amirghodsi , Kevin Wampler , Elya Shechtman , Aliakbar Darabi
Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for improved patch validity testing for patch-based synthesis applications using similarity transforms. The improved patch validity tests are used to validate (or invalidate) candidate patches as valid patches falling within a sampling region of a source image. The improved patch validity tests include a hole dilation test for patch validity, a no-dilation test for patch invalidity, and a comprehensive pixel test for patch invalidity. A fringe test for range invalidity can be used to identify pixels with an invalid range and invalidate corresponding candidate patches. The fringe test for range invalidity can be performed as a precursor to any or all of the improved patch validity tests. In this manner, validated candidate patches are used to automatically reconstruct a target image.
-
公开(公告)号：US10402948B2
公开(公告)日：2019-09-03
申请号：US16009714
申请日：2018-06-15
Applicant: ADOBE INC.
Inventor： Sylvain Paris , Sohrab Amirghodsi , Aliakbar Darabi , Elya Shechtman
Abstract: Embodiments described herein are directed to methods and systems for facilitating control of smoothness of transitions between images. In embodiments, a difference of color values of pixels between a foreground image and the background image are identified along a boundary associated with a location at which to paste the foreground image relative to the background image. Thereafter, recursive down sampling of a region of pixels within the boundary by a sampling factor is performed to produce a plurality of down sampled images having color difference indicators associated with each pixel of the down sampled images. Such color difference indicators indicate whether a difference of color value exists for the corresponding pixel. To effectuate a seamless transition, the color difference indicators are normalized in association with each recursively down sampled image.
-
Patent Agency Ranking
公开(公告)号：US20250061626A1
公开(公告)日：2025-02-20
申请号：US18674518
申请日：2024-05-24
Applicant: Adobe Inc.
Inventor： Xiaoyang Liu , Zhe Lin , Yuqian Zhou , Sohrab Amirghodsi , Sarah Jane Stuckey , Sakshi Gupta , Guotong Feng , Elya Schechtman , Connelly Stuart Barnes , Betty Leong
IPC: G06T11/60 , G06T5/77 , G06T11/20 , G06V10/764
Abstract: Techniques for performing a digital operation on a digital image are described along with methods and systems employing such techniques. According to the techniques, an input (e.g., an input stroke) is received by, for example, a processing system. Based upon the input, an area of the digital image upon which a digital operation (e.g., for removal of a distractor within the area) is to be performed is determined. In an implementation, one or more metrics of an input stroke are analyzed, typically in real time, to at least partially determine the area upon which the digital operation is to be performed. In an additional or alternative implementation, the input includes a first point, a second point and a connector, and the area is at least partially determined by a location of the first point relative to a location of the second point and/or by locations of the first point and/or second point relative to one or more edges of the digital image.
-
公开(公告)号：US20240362791A1
公开(公告)日：2024-10-31
申请号：US18307353
申请日：2023-04-26
Applicant: Adobe Inc.
Inventor： Yuqian Zhou , Chuong Huynh , Connelly Barnes , Elya Shechtman , Sohrab Amirghodsi , Zhe Lin
IPC: G06T7/12 , G06F3/04883 , G06V10/44 , G06V10/74 , G06V10/80
CPC classification number: G06T7/12 , G06F3/04883 , G06V10/44 , G06V10/761 , G06V10/806 , G06T2207/20101 , G06V2201/07
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing machine learning to generate a mask for an object portrayed in a digital image. For example, in some embodiments, the disclosed systems utilize a neural network to generate an image feature representation from the digital image. The disclosed systems can receive a selection input identifying one or more pixels corresponding to the object. In addition, in some implementations, the disclosed systems generate a modified feature representation by integrating the selection input into the image feature representation. Moreover, in one or more embodiments, the disclosed systems utilize an additional neural network to generate a plurality of masking proposals for the object from the modified feature representation. Furthermore, in some embodiments, the disclosed systems utilize a further neural network to generate the mask for the object from the modified feature representation and/or the masking proposals.
-
公开(公告)号：US20240303787A1
公开(公告)日：2024-09-12
申请号：US18179855
申请日：2023-03-07
Applicant: Adobe Inc.
Inventor： Yuqian Zhou , Connelly Barnes , Zijun Wei , Zhe Lin , Elya Shechtman , Sohrab Amirghodsi , Xiaoyang Liu
CPC classification number: G06T5/77 , G06T7/11 , G06V20/176 , G06T2207/20021 , G06T2207/30184
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for inpainting a digital image using a hybrid wire removal pipeline. For example, the disclosed systems use a hybrid wire removal pipeline that integrates multiple machine learning models, such as a wire segmentation model, a hole separation model, a mask dilation model, a patch-based inpainting model, and a deep inpainting model. Using the hybrid wire removal pipeline, in some embodiments, the disclosed systems generate a wire segmentation from a digital image depicting one or more wires. The disclosed systems also utilize the hybrid wire removal pipeline to extract or identify portions of the wire segmentation that indicate specific wires or portions of wires. In certain embodiments, the disclosed systems further inpaint pixels of the digital image corresponding to the wires indicated by the wire segmentation mask using the patch-based inpainting model and/or the deep inpainting model.
-
19.发明公开公开(公告)号：US20230385992A1
公开(公告)日：2023-11-30
申请号：US17664991
申请日：2022-05-25
Applicant: Adobe Inc.
Inventor： Connelly Barnes , Elya Shechtman , Sohrab Amirghodsi , Zhe Lin
CPC classification number: G06T5/005 , G06T5/50 , G06T2207/20084 , G06T2207/20212 , G06T2207/10024
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that implement an inpainting framework having computer-implemented machine learning models to generate high-resolution inpainting results. For instance, in one or more embodiments, the disclosed systems generate an inpainted digital image utilizing a deep inpainting neural network from a digital image having a replacement region. The disclosed systems further generate, utilizing a visual guide algorithm, at least one deep visual guide from the inpainted digital image. Using a patch match model and the at least one deep visual guide, the disclosed systems generate a plurality of modified digital images from the digital image by replacing the region of pixels of the digital image with replacement pixels. Additionally, the disclosed systems select, utilizing an inpainting curation model, a modified digital image from the plurality of modified digital images to provide to a client device.
-
公开(公告)号：US11823313B2
公开(公告)日：2023-11-21
申请号：US17332773
申请日：2021-05-27
Applicant: Adobe Inc.
Inventor： Xin Sun , Sohrab Amirghodsi , Nathan Carr , Michal Lukac
CPC classification number: G06T11/60 , G06V10/758
Abstract: The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating a modified digital image by identifying patch matches within a digital image utilizing a Gaussian mixture model. For example, the systems described herein can identify sample patches and corresponding matching portions within a digital image. The systems can also identify transformations between the sample patches and the corresponding matching portions. Based on the transformations, the systems can generate a Gaussian mixture model, and the systems can modify a digital image by replacing a target region with target matching portions identified in accordance with the Gaussian mixture model.
-
-
-
-
-
-
-
-
-
Search Results
73
records
(took 0.015 seconds)
